NVIDIA releases Nemotron 3.5 Bolt E4B, a 4GB open model for local agents
READ THE ORIGINAL SOURCEOpen original sourceresearch.nvidia.com · Opens in a new tabNVIDIA announces Nemotron 3.5 Bolt E4B 4GB, an open small language model built on Gemma 4 E4B with Nemotron post-training, aimed at conversational agents on local hardware. The report says it offers about 40% higher average quality than NVIDIA's prior model, Nano 4B, on conversational agent benchmarks, and up to about 80% fewer output tokens than peers. It supports multi-turn tool use, a conversational mode, configurable reasoning, a 64k context, and 35 languages. Performance figures are reported across RTX, Jetson, and DGX Spark hardware using Q4_K_M quantization.
One primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · automated brief
- Discovery linkX
- Linked in sourceTechnical Report
- Linked in sourceNemotron 3.5 Bolt E4B 4GB
- Linked in sourceGeForce RTX
- Linked in sourceJetson
- Linked in sourceRTX Spark
- Linked in sourceDGX Spark
- Linked in sourceprior model
- Linked in sourceInverseIFEval
- Linked in sourceGemma4-E4B-it
- Linked in sourceNeMo-RL
- Linked in sourceNeMo-Gym
- Linked in sourcehere
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
NVIDIA announces Nemotron 3.5 Bolt E4B 4GB, an open small language model built on Gemma 4 E4B with Nemotron post-training, aimed at conversational agents on local hardware. The report says it offers about 40% higher average quality than NVIDIA's prior model, Nano 4B, on conversational agent benchmarks, and up to about 80% fewer output tokens than peers. It supports multi-turn tool use, a conversational mode, configurable reasoning, a 64k context, and 35 languages. Performance figures are reported across RTX, Jetson, and DGX Spark hardware using Q4_K_M quantization.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: research.nvidia.com. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; benchmark comparisons are reported by NVIDIA and some evaluations, including Brevity Bench and When2Call-MT, were noted as to be released later.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Bolt E4B reports about 40% higher average benchmark scores than the prior Nano 4B model across the cited conversational and agentic benchmarks.
- The model supports multi-turn tool use, a conversational mode for speech-ready replies, and configurable reasoning with a 64k context window.
- Reported single-session results include about 15.5 tokens/s on Jetson Orin Nano 8GB and 133.4 tokens/s on RTX 5070 at 3K input, 50 output.
- Benchmark results come from NVIDIA's own evaluation setup and may vary with hardware, inference software, and configuration.
Source claims not independently checked; benchmark comparisons are reported by NVIDIA and some evaluations, including Brevity Bench and When2Call-MT, were noted as to be released later.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
NVIDIA's Oct 23 page says Bolt E4B builds on Gemma 4 E4B with Nemotron post-training, ships open weights, data and recipes, and targets local assistants and robots on RTX/Jetson. Quality gains (~40% vs its prior model) are NVIDIA's claim.
Source claims not independently checked; benchmark comparisons are reported by NVIDIA and some evaluations, including Brevity Bench and When2Call-MT, were noted as to be released later.
- Bot tagged: supports Scale's MultiChallenge leaderboard ranks Bolt E4B first among small models at 56.03%, 12.8 points ahead of Gemma 4 E4B. Inspect post ↗
- Bot tagged: context Unsloth published GGUF builds and says the model runs locally on about 6GB RAM. Inspect post ↗
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
- x post ↗ · 1,912 likes, 232 reposts, 129 replies, 128 quotes · observed 10/24/2026, 10:02:28 PM
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
Small, local models that handle dialogue and tool calls within a few gigabytes of memory could enable responsive assistants on consumer and embedded devices without cloud latency or privacy tradeoffs.
Limits and open questions
Source claims not independently checked; benchmark comparisons are reported by NVIDIA and some evaluations, including Brevity Bench and When2Call-MT, were noted as to be released later.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.